© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65464
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on numeric constants (multi‐digit numbers) in mathematical expressions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEGGI
    -0.95
    ultades
    -0.89
     видом
    -0.88
     принад
    -0.87
    戰鬥
    -0.86
    CÓMO
    -0.86
     lavet
    -0.85
    赘
    -0.85
    ändigen
    -0.85
    During
    -0.85
    POSITIVE LOGITS
     trám
    1.18
     everyone
    1.07
     tuot
    1.04
     erziel
    1.01
    ramienta
    0.98
     Reſ
    0.98
    作品
    0.97
     correa
    0.93
     COUR
    0.93
     áng
    0.92
    Activations Density 0.017%

    No Known Activations